WhichAI / Models / Gemma 4 26B A4B

Gemma 4 26B A4B

· verified October 13, 2026

public paid api free open-weights vision local

Provider

Statuspublic

AA Intelligence Index16.7 (official, read October 13, 2026)

Released2026-04-03

Context window262K

ModalitiesText + image + video

API price $/1M (in / out)$0.09 / $0.3 (OpenRouter)

Speedn/a

AccessAPI $0.09/$0.3 per 1M tokens on OpenRouter · free route on OpenRouter (google/gemma-4-26b-a4b-it:free) · open weights · listed April 3, 2026

In one line

Gemma 4 26B A4B by Google, measured by Artificial Analysis at 16.7 on the Intelligence Index, 39.3 on coding and 2.9 on agentic work. Added to WhichAI automatically from live data on October 13, 2026: no editorial review yet, so judge it by the numbers, not by a verdict. OpenRouter's description: “Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.”

Alternatives worth a look

DeepSeek V3.2 Exp (DeepSeek) · AA 16.6API $0.27/$0.41 per 1M tokens on OpenRouter · open weights · listed September 29, 2025
Claude Haiku 4.5 (Anthropic) · AA 16.9All Claude tiers · cheapest Claude via API
Step 3.5 Flash (StepFun) · AA 17API $0.1/$0.3 per 1M tokens on OpenRouter · open weights · listed January 29, 2026

Open Gemma's official app ↗ Open in the WhichAI app Not sure? Take the 30-second finder

Artificial Analysis Intelligence Index, official scale (the number published on artificialanalysis.ai), relayed by OpenRouter and refreshed automatically: last read October 13, 2026. 210 models carry a current official measurement. A value marked ~ is converted from an earlier snapshot because no current measurement is published; an unmeasured model is never ranked. Context, price, modality and listing dates come from the public OpenRouter model list (refreshed automatically on the live site; static copy retrieved October 3, 2026) and vendor pages. Missing values are not published or not yet verified - shown as -. Sources are linked inside the app (the Ranking chapter and About > Methodology).